Research Article
Novel Discrete Compactness-Based Training for Vector Quantization Networks: Enhancing Automatic Brain Tissue Classification
Table 14
Associations between winner classes and tissue characterizations for network topology
. There is a set of
If-Then rules for each evaluation set.
| | First set | Second set | | If winner class is | Then characterize mask as | If winner class is | Then characterize mask as |
| | 0 | Background-0 | 0 | Fat-4 | | 1 | Background-0 | 1 | Background-0 | | 2 | Background-0 | 2 | Fat-4 | | 3 | Skull-7 | 3 | Skin-6 | | 4 | Grey Matter-2 | 4 | Connective-9 | | 5 | Background-0 | 5 | Background-0 | | 6 | Background-0 | 6 | Background-0 | | 7 | Background-0 | 7 | Fat-4 | | 8 | White Matter-3 | 8 | White matter-3 | | 9 | Background-0 | 9 | Fat-4 | | 10 | Skin-6 | 10 | Grey matter-2 | | 11 | Background-0 | 11 | Fat-4 | | 12 | Background-0 | 12 | Fat-4 | | 13 | Background-0 | 13 | Fat-4 | | 14 | Background-0 | 14 | Fat-4 | | 15 | Background-0 | 15 | Skin-6 | | 16 | Background-0 | 16 | Fat-4 | | 17 | Background-0 | 17 | Fat-4 | | 18 | CSF-1 | 18 | Fat-4 | | 19 | CSF-1 | 19 | Fat-4 |
|
|
